Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    hammer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expectations
    -0.09
    ioxid
    -0.08
     expectativas
    -0.08
    Expect
    -0.07
     extracellular
    -0.07
     expectation
    -0.07
     checksum
    -0.07
    Tax
    -0.07
     calibr
    -0.07
     thao
    -0.07
    POSITIVE LOGITS
     Sheet
    0.09
    upon
    0.09
     Gare
    0.09
     añad
    0.09
     Upon
    0.08
    幸
    0.08
    хны
    0.08
     Automat
    0.08
     жилийн
    0.08
     Anzeigen
    0.08
    Act Density 0.004%

    No Known Activations